Learning Autonomous Driving in Simulation @AAmini

Uploaded September 2020 | Updated September 2026, 2 weeks ago

A TechCrunch spotlight feature covering a brand new data-driven simulation engine, developed at MIT, capable of training full-scale autonomous vehicles in simulation for deployment in the real-world. This project represented the first time a virtual vehicle, trained using reinforcement learning, was able to learn entirely in simulation and be successfully deployed onto real roads.

To learn more about our simulator (VISTA) and this project:
Project website: bit.ly/VISTA-sim
Technical Paper: ieeexplore.ieee.org/document/8957584
Code: coming soon!! https://forms.gle/4CzEou4Ffs9Lg9dr7

Learning Autonomous Driving in Simulation

MIT 6.S191: Convolutional Neural Networks

MIT 6.S191 (2021): Recurrent Neural Networks

MIT 6.S191 (2020): Deep Generative Modeling

MIT 6.S191 (2018): Deep Reinforcement Learning

MIT 6.S191: Automatic Speech Recognition

MIT 6.S191 (2020): Deep Learning New Frontiers

MIT 6.S191 (2025): Reinforcement Learning

MIT 6.S191: Evidential Deep Learning and Uncertainty

MIT 6.S191 (2022): Convolutional Neural Networks

MIT 6.S191 (2019): Visualization for Machine Learning (Google Brain)